Agent Md Refactor
softaworks/agent-toolkitAn AI agent's instruction file should be easy to read and understand. Over time these files can grow very long. They become hard to manage.
This skill helps you organize the file into a clear structure. You will find contradictions and remove confusing parts. The result is a clean set of instructions that are simple to update.
You keep only the essential rules in the main file. Then you move the rest into separate linked documents. This approach is called progressive disclosure. It makes your agent instructions much easier to work with.
Add Agent Md Refactor skill to your workflow
Global
mkdir -p ~/.claude/skills/agent-md-refactorProject
mkdir -p .claude/skills/agent-md-refactorSource Repository
More Prompt Engineering & Context Engineering Claude Code Skills
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time